© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18539
    Prev
    Next
    INDEX
    Explanations

    ac-dc, ac power, ac voltage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugal
    -0.09
    edly
    -0.09
    аем
    -0.08
    pread
    -0.08
    åĦ¿çļĦ
    -0.07
    eded
    -0.07
    odor
    -0.07
    ãģ¦ãģĦãĤĭ
    -0.07
    é«ĺçŃīä¸ĵç§ijåŃ¦æł¡
    -0.07
    edImage
    -0.07
    POSITIVE LOGITS
    robat
    0.09
    ../../
    0.08
    raft
    0.08
    uity
    0.08
    quires
    0.08
    worth
    0.08
    ترØŃ
    0.07
    uña
    0.07
    ساÙĩ
    0.07
    avanaugh
    0.07
    Activations Density 0.065%

    No Known Activations